5 papers
PerfCoder: Large Language Models for Interpretable Code Performance Optimization
Jiuding Yang, Shengyao Lu, Hongxuan Liu +4
Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirem…
Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
Muhammad Kamran Janjua, Hugo Silva, Di Niu +1
Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-…
Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants
Jiuding Yang, Weidong Guo, Kaitong Yang +3
The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhan…
TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution
Jiuding Yang, Shengyao Lu, Weidong Guo +4
Large Language Models (LLMs) require precise alignment with complex instructions to optimize their performance in real-world applications. As the demand for refined instruction tun…
Instruction Fusion: Advancing Prompt Evolution through Hybridization
Weidong Guo, Jiuding Yang, Kaitong Yang +4
The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, e…